Dual-branch residual network for lung nodule segmentation

An accurate segmentation of lung nodules in computed tomography (CT) images is critical to lung cancer analysis and diagnosis. However, due to the variety of lung nodules and the similarity of visual characteristics between nodules and their surroundings, a robust segmentation of nodules becomes a challenging problem. In this study, we propose the Dual-branch Residual Network (DB-ResNet) which is a data-driven model. Our approach integrates two new schemes to improve the generalization capability of the model: (1) the proposed model can simultaneously capture multi-view and multi-scale features of different nodules in CT images; (2) we combine the features of the intensity and the convolutional neural networks (CNN). We propose a pooling method, called the central intensity-pooling layer (CIP), to extract the intensity features of the center voxel of the block, and then use the CNN to obtain the convolutional features of the center voxel of the block. In addition, we designed a weighted sampling strategy based on the boundary of nodules for the selection of those voxels using the weighting score, to increase the accuracy of the model. The proposed method has been extensively evaluated on the LIDC-IDRI dataset containing 986 nodules. Experimental results show that the DB-ResNet achieves superior segmentation performance with the dice similarity coefficient (DSC) of 82.74% on the dataset. Moreover, we compared our results with those of four radiologists on the same dataset. The comparison showed that our DSC was 0.49% higher than that of human experts. This proves that our proposed method is as good as the experienced radiologist.     

CT影像肺结节分割研究进展

准确分割肺结节在临床上具有重要意义。计算机断层扫描（computer tomography,CT）技术以其成像速度快、图像分辨率高等优点广泛应用于肺结节分割及功能评价中。为了进一步对肺部CT影像中的肺结节分割方法进行探索,本文对基于CT影像的肺结节分割方法研究进行综述。1）对传统的肺结节分割方法及其优缺点进行了归纳比较;2）重点介绍了包括深度学习、深度学习与传统方法相结合在内的肺结节分割方法;3）简单介绍了肺结节分割方法的常用评价指标,并结合部分方法的指标表现展望了肺结节分割方法研究领域的未来发展趋势。传统的肺结节分割方法各有优缺点和其适用的结节类型,深度学习分割方法因普适性好等优点成为该领域的研究热点。研究者们致力于如何提高分割结果的准确度、模型的鲁棒性及方法的普适性,为了实现此目的本文总结了各类方法的优缺点。基于CT影像的肺结节分割方法研究已经取得了不小的成就,但肺结节形状各异、密度不均匀,且部分结节与血管、胸膜等解剖结构粘连,给结节分割增加了困难,结节分割效果仍有很大提升空间。精度高、速度快的深度学习分割方法将会是研究者密切关注的方法,但该类方法仍需解决数据需求量大和网络模型超参数的确定等问题。     

融合双注意力机制3D U-Net的肺肿瘤分割

目的 精确的肺肿瘤分割对肺癌诊断、手术规划以及放疗具有重要意义。计算机断层扫描（computed tomography,CT）是肺癌诊疗中最重要的辅助手段,但阅片是一项依靠医生主观经验、劳动密集型的工作,容易造成诊断结果的不稳定,实现快速、稳定和准确的肺肿瘤自动分割方法是当前研究的热点。随着深度学习的发展,使用卷积神经网络进行肺肿瘤的自动分割成为了主流。本文针对3D U-Net准确度不足,容易出现假阳性的问题,设计并实现了3维卷积神经网络DAU-Net（dual attention U-Net）。方法 首先对数据进行预处理,调整CT图像切片内的像素间距,设置窗宽、窗位,并通过裁剪去除CT图像中的冗余信息。DAU-Net以3D U-Net为基础结构,将每两个相邻的卷积层替换为残差结构,并在收缩路径和扩张路径中间加入并联在一起的位置注意力模块和通道注意力模块。预测时,采用连通域分析对网络输出的二值图像进行后处理,通过判断每个像素与周围26个像素的连通关系获取所有的连通域,并清除最大连通域外的其他区域,进一步提升分割精度。结果 实验数据来自上海胸科医院,总共1 010例肺癌患者,每例数据只包含一个病灶,专业的放射科医师提供了金标准,实验采用十折交叉验证。结果表明,本文提出的肺肿瘤分割算法与3D U-Net相比,Dice系数和哈斯多夫距离分别提升了2.5%和9.7%,假阳性率减少了13.6%。结论 本文算法能够有效提升肺肿瘤的分割精度,有助于实现肺癌的快速、稳定和准确分割。     

Deep Fuzzy SegNet-based lung nodule segmentation and optimized deep learning for lung cancer detection

Pattern Analysis and Applications - Globally, lung cancer has a high fatality rate and is a lethal disease. Since lung cancer affects both men and women, it requires extra consideration when...     

Topological Active Volume 3D segmentation model optimized with genetic approaches

The Topological Active Volumes is an active model focused on 3D segmentation tasks. It is based on the 2D Topological Active Nets model and provides information about the surfaces and the inside of the detected objects in the scene. This paper proposes new optimization approaches based on Genetic Algorithms that improve the results of the 3D segmentations and overcome some drawbacks of the model related to parameter tuning or noise conditions. The hybridization of the genetic algorithm with a greedy local search allows the treatment of topological changes in the model, with the possibility of an automatic subdivision of the Topological Active Volume. This combination integrates the advantages of the global and local search procedures in the segmentation process.     

3D Object retrieval based on viewpoint segmentation

In the last decades, extensive efforts have been dedicated to develop better 3D object retrieval methods. View-based methods have attracted a significant amount of attention, not only because of their state-of-the-art performance, but also they merely require some of a 3D object’s 2D view images. However, most recent approaches only deal with the images’ content difference without the discrepancy of view relative positions. In this paper, we propose a normal method for view segmentation, based on Markov random field (MRF) model, which consider not only the difference between the content of views but also the relative locations. Each view is obtained by projecting at certain viewpoints and angels, therefore, these locations can be applied to depict each view, with content of views. We use the MRF to implement view segmentation and choose the representative views. Finally, we present a framework based on the proposed view segmentation method for 3D object retrieval and the experimental results demonstrate that the proposed method can achieve better retrieval effectiveness than state-of-the-art methods under several standard evaluation measures.     

基于深度迁移学习的肺结节分割方法

针对U-Net分割小体积肺结节效果较差的问题,提出一种基于深度迁移学习的分割方法,利用分块式叠加微调（BSFT）策略辅助分割肺结节。首先,利用卷积神经网络学习自然图像大数据集的特征信息;然后,将所学特征迁移到进行肺结节图像小数据集分割的网络,从该网络最后一个下采样层开始逐块释放、微调训练,直到网络完成最后一层的叠加;最后,定量分析Dice相似性系数,以确定最佳分割网络。实验结果表明,BSFT在LUNA16肺结节公开数据集上的Dice值达到0.917 9,该策略的性能明显优于主流肺结节分割算法。     

保边滤波和改进FCM的疑似肺结节分割方法

提出一种基于保边滤波和改进FCM算法的疑似肺结节自动分割方法。首先,分离出边缘光滑的肺实质并通过非线性各向异性扩散滤波增强肺区疑似病灶,然后运用改进的模糊C-均值聚类算法分割出不同大小的疑似肺结节。实验结果证明,该方法能够自动、准确地完成疑似肺结节分割,比用传统的FCM算法取得更佳效果,并具有良好的鲁棒性和效率。     

优化的PCNN自适应三维图像分割算法*

脉冲耦合神经网络(pulse coupled neural network,PCNN)对图像分割具有天然的优势,但是传统的PCNN模型参数难以确定,且算法耗时多。对多种PCNN模型进行研究改进,并利用统计学知识提出了一种精简高效的自适应三维分割算法。将其用于脑部磁共振成像(magnetic resonance imaging,MRI)图像的分割,把脑组织分成白质、灰质和脑脊液。与标准PCNN、传统的Otsu阈值方法、SPM8工具箱及专家手动分割结果的对比实验表明,该自适应算法具有精确性、高效性。     

Graph-cut based interactive segmentation of 3D materials-science images

Segmenting materials’ images is a laborious and time-consuming process, and automatic image segmentation algorithms usually contain imperfections and errors. Interactive segmentation is a growing topic in the areas of image processing and computer vision, which seeks to find a balance between fully automatic methods and fully-manual segmentation processes. By allowing minimal and simplistic interaction from the user in an otherwise automatic algorithm, interactive segmentation is able to simultaneously reduce the time taken to segment an image while achieving better segmentation results. Given the specialized structure of materials’ images and level of segmentation quality required, we show an interactive segmentation framework for materials’ images that has three key contributions: (1) a multi-labeling approach that can handle a large number of structures while still quickly and conveniently allowing manual addition and removal of segments in real-time, (2) multiple extensions to the interactive tools which increase the simplicity of the interaction, and (3) a web interface for using the interactive tools in a client/server architecture. We show a full formulation of each of these contributions and example results from their application.     

基于语义分割引导的三维目标检测

三维目标检测是计算机视觉领域的热门研究内容之一。在自动驾驶系统中,三维目标检测技术通过捕获周围的点云信息与RGB图像信息,对周围物体进行检测,从而为车辆规划下一步的行进路线。因此,通过三维目标检测实现对周边环境的精准检测与感知是十分重要的。针对三维目标检测技术中随机采样算法导致前景点丢失的问题,首先提出了基于语义分割的随机采样算法,通过预测的语义特征指导采样过程,提升了前景点的采样比重,进而提高了三维目标检测精度;其次,针对三维目标检测定位置信度与分类置信度不一致的问题,提出了CL联合损失,使得网络倾向于选择定位置信度与分类置信度都高的3D候选框,避免了传统的NMS仅考虑分类置信度所带来的歧义问题。在KITTI三维目标检测数据集进行了实验,结果表明,该方法能够在简单、中等、困难3个难度下均获得精度的提升,从而验证了其在三维目标检测任务中的有效性。     

Deep residual neural network based PointNet for 3D object part segmentation

Multimedia Tools and Applications - Point cloud segmentation is the premise and basis of many 3D perception tasks, such as intelligent driving, object detection and recognition, scene recognition...     

网格分割的3维网格模型非盲水印算法

目的 信息技术的发展使得面向3维模型版权保护的问题越来越突出,提出一种新的基于网格分割的3维网格模型非盲水印算法。方法 首先使用基于形状直径函数的网格分割算法对3维网格模型进行有意义的网格分割,然后计算每个分块的鲁棒重心并以此为中心将模型由直角坐标系转换到球面坐标系,最后通过调制每个顶点范数的分布来嵌入水印,在水印检测阶段使用非盲检测的方法提取水印。结果 针对目前基于网格分块的水印算法的网格分割不一致以及对分割边界依赖性过强等问题,引入基于形状直径函数的网格分割算法并在重对齐、重采样过程中加入待检测模型与原始模型分块匹配过程以保证网格分割的一致性,并且选取分块的顶点范数的分布作为水印嵌入基元,使得算法能够有效地减弱对分割边界的依赖性。结论 实验结果表明,该算法可以有效抵抗平移、旋转、缩放、噪声、细分、简化、剪切等常见的攻击以及多种攻击的联合攻击。     

A 3D nodule candidate detection method supported by hybrid features to reduce false positives in lung nodule detection

Multimedia Tools and Applications - Lungs cancer is a fatal disease. However, its early detection increases the chances of survival among patients. An automated nodule detection system provides the...     

基于区域离散曲率的三维网格分水岭分割

针对离散曲率估计对噪声敏感且特征值计算量大的特点提出了基于区域离散曲率的三维网格分水岭分割算法。寻找三维模型显著特征点;对三维模型进行预分割,确定分割带;在分割带区域上计算离散曲度极值点,利用测地距离和曲度极值点对三维模型进行分水岭分割。算法在分割前无需进行网格去噪,实验结果证明,对主体分支明显的模型具有较高的分割边缘准确度和较快的分割速度。     

基于3D路径聚合高分辨率网络的胰腺分割

目的 胰腺的准确分割是胰腺癌识别和分析的重要前提。现有基于深度学习的主流胰腺分割网络大多是编码—解码结构,对特征图采用先降低再增加分辨率的方式,严重丢失了胰腺位置和细节信息,导致分割效果不佳。针对上述问题,提出了基于3D路径聚合高分辨率网络的胰腺分割方法。方法 首先,为了捕获更多3D特征上下文信息,将高分辨率网络中的2D运算拓展为3D运算;其次,提出全分辨特征路径聚合模块,利用连续非线性变换缩小全分辨率输入图像与分割头网络输出特征语义差异的同时,减少茎网络下采样丢失的位置和细节信息对分割结果的影响;最后,提出多尺度特征路径聚合模块,利用渐进自适应特征压缩融合方式,避免低分辨率特征通道过度压缩导致的信息内容损失。结果 在公开胰腺数据集上,提出方法在Dice系数（Dice similarity coefficient,DSC）、Jaccard系数（Jaccard index,JI）、精确率（precision）和召回率（recall）上相比3D高分辨率网络（3D high-resolution net,3DHRNet）分别提升了1.41%、2.09%、2.35%和0.49%,相比具有代表性编码—解码结构的胰腺分割方法,取得了更高的分割精度。结论 本文提出的3D路径聚合高分辨率网络（3D pathaggregation high-resolution network,3DPAHRNet）具有更强的特征位置和细节信息的保留能力,能够显著改善在腹部CT（computed tomography）图像中所占比例较小的胰腺器官的分割结果。开源代码可在https：//github.com/qiuchengjian/PAHRNet3D获得。     

基于SLIC区域分割的三维地形重建算法

为利用无人机在高空连续拍摄的两幅航拍图像准确实现三维地形重建,提出了通过将图像进行区域分割来达到不同地形区域分别生成数字高程模型DEM数据的方法。首先利用简单线性迭代聚类SLIC超像素算法将图像分割为多个包含单一地形的超像素区域,再利用各区域的颜色信息进行相邻同类地形区域的融合,最后在所得的各区域内通过SIFT特征点提取与匹配、计算三维坐标来生成DEM数据。通过将重建地形结果与卫星地图对比表明,利用该方法能够有效实现地形重建;通过对比本文算法与传统地形重建算法的重建结果表明,利用该方法能准确呈现各地形间的边界信息。     

基于PCNN与主动轮廓的肺CT候选结节的分割方法*

对肺CT图像中的候选结节进行分割,是计算机辅助诊断系统完成对肺结节自动检测、分类重要的步骤。然而,由于成像噪音和病变导致的图像中组织及组织与病灶之间边界模糊,故采用通常的图像分割方法难以获得正确的分割结果。文章提出一种结合四邻域连接权的脉冲耦合神经网络(PCNN)结合先验形状能量函数的主动轮廓模型来分割候选肺内与近胸膜两类肺结节的算法。实验表明,该算法是一种切实可行且行之有效的候选肺CT结节分割方法。